From: Fred Drake Date: Sat, 17 May 2008 21:14:05 +0000 (+0000) Subject: update references and documentation for modules in the new html package X-Git-Tag: v2.6b1~348 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=cb51d84214ed07268338392abef986b9a56d0141;p=thirdparty%2FPython%2Fcpython.git update references and documentation for modules in the new html package (http://bugs.python.org/issue2882) --- diff --git a/Doc/library/htmllib.rst b/Doc/library/htmllib.rst index 96a7d0812598..ffaaaece6da9 100644 --- a/Doc/library/htmllib.rst +++ b/Doc/library/htmllib.rst @@ -77,12 +77,12 @@ The module defines a parser class and an exception: Interface definition for transforming an abstract flow of formatting events into specific output events on writer objects. - Module :mod:`HTMLParser` + Module :mod:`html.parser` Alternate HTML parser that offers a slightly lower-level view of the input, but is designed to work with XHTML, and does not implement some of the SGML syntax not used in "HTML as deployed" and which isn't legal for XHTML. - Module :mod:`htmlentitydefs` + Module :mod:`html.entities` Definition of replacement text for XHTML 1.0 entities. Module :mod:`sgmllib` @@ -149,10 +149,10 @@ additional methods and instance variables for use within tag methods. :meth:`save_bgn` will raise a :exc:`TypeError` exception. -:mod:`htmlentitydefs` --- Definitions of HTML general entities -============================================================== +:mod:`html.entities` --- Definitions of HTML general entities +============================================================= -.. module:: htmlentitydefs +.. module:: html.entities :synopsis: Definitions of HTML general entities. .. sectionauthor:: Fred L. Drake, Jr. diff --git a/Doc/library/htmlparser.rst b/Doc/library/htmlparser.rst index 85a38fbe9816..ee3e1f27b0a5 100644 --- a/Doc/library/htmlparser.rst +++ b/Doc/library/htmlparser.rst @@ -1,8 +1,8 @@ -:mod:`HTMLParser` --- Simple HTML and XHTML parser -================================================== +:mod:`html.parser` --- Simple HTML and XHTML parser +=================================================== -.. module:: HTMLParser +.. module:: html.parser :synopsis: A simple parser that can handle HTML and XHTML. @@ -22,7 +22,7 @@ in :mod:`sgmllib`. The :class:`HTMLParser` class is instantiated without arguments. - An HTMLParser instance is fed HTML data and calls handler functions when tags + An :class:`HTMLParser` instance is fed HTML data and calls handler functions when tags begin and end. The :class:`HTMLParser` class is meant to be overridden by the user to provide a desired behavior. @@ -92,8 +92,8 @@ An exception is defined as well: ``handle_starttag('a', [('href', 'http://www.cwi.nl/')])``. .. versionchanged:: 2.6 - All entity references from htmlentitydefs are now replaced in the attribute - values. + All entity references from :mod:`html.entities` are now replaced in the + attribute values. .. method:: HTMLParser.handle_startendtag(tag, attrs) @@ -171,7 +171,7 @@ Example HTML Parser Application As a basic example, below is a very basic HTML parser that uses the :class:`HTMLParser` class to print out tags as they are encountered:: - from HTMLParser import HTMLParser + from html.parser import HTMLParser class MyHTMLParser(HTMLParser): diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 2cbc2ecbc732..b5010ac0970d 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -372,16 +372,17 @@ class HTMLParser(markupbase.ParserBase): c = int(s) return unichr(c) else: - # Cannot use name2codepoint directly, because HTMLParser supports apos, - # which is not part of HTML 4 - import htmlentitydefs + # Cannot use name2codepoint directly, because HTMLParser + # supports apos, which is not part of HTML 4 + import html.entities if HTMLParser.entitydefs is None: entitydefs = HTMLParser.entitydefs = {'apos':u"'"} - for k, v in htmlentitydefs.name2codepoint.iteritems(): + for k, v in html.entities.name2codepoint.iteritems(): entitydefs[k] = unichr(v) try: return self.entitydefs[s] except KeyError: return '&'+s+';' - return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s) + return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", + replaceEntities, s) diff --git a/Lib/htmllib.py b/Lib/htmllib.py index 24a2e2f3c71f..7ebb622e89a5 100644 --- a/Lib/htmllib.py +++ b/Lib/htmllib.py @@ -24,7 +24,7 @@ class HTMLParser(sgmllib.SGMLParser): """ - from htmlentitydefs import entitydefs + from html.entities import entitydefs def __init__(self, formatter, verbose=0): """Creates an instance of the HTMLParser class. diff --git a/Lib/test/test_codeccallbacks.py b/Lib/test/test_codeccallbacks.py index 656551d7c0fe..a0fa34347deb 100644 --- a/Lib/test/test_codeccallbacks.py +++ b/Lib/test/test_codeccallbacks.py @@ -1,5 +1,5 @@ import test.test_support, unittest -import sys, codecs, htmlentitydefs, unicodedata +import sys, codecs, html.entities, unicodedata class PosReturn: # this can be used for configurable callbacks @@ -86,7 +86,7 @@ class CodecCallbackTest(unittest.TestCase): l = [] for c in exc.object[exc.start:exc.end]: try: - l.append(u"&%s;" % htmlentitydefs.codepoint2name[ord(c)]) + l.append(u"&%s;" % html.entities.codepoint2name[ord(c)]) except KeyError: l.append(u"&#%d;" % ord(c)) return (u"".join(l), exc.end) diff --git a/Lib/test/test_multibytecodec_support.py b/Lib/test/test_multibytecodec_support.py index 60557640be3f..b9aa34b44418 100644 --- a/Lib/test/test_multibytecodec_support.py +++ b/Lib/test/test_multibytecodec_support.py @@ -64,7 +64,7 @@ class TestBase: if self.has_iso10646: return - from htmlentitydefs import codepoint2name + from html.entities import codepoint2name def xmlcharnamereplace(exc): if not isinstance(exc, UnicodeEncodeError): diff --git a/Lib/test/test_sundry.py b/Lib/test/test_sundry.py index 404a405de5ec..c2fb66d99ec2 100644 --- a/Lib/test/test_sundry.py +++ b/Lib/test/test_sundry.py @@ -50,7 +50,7 @@ class TestUntestedModules(unittest.TestCase): import encodings import formatter import getpass - import htmlentitydefs + import html.entities import ihooks import imghdr import imputil